Microsoft (United States)

Who Grades the Grader? The Verification Gap in Self-Testing Code Agents

When a coding agent writes both code and tests, the two can agree while sharing the same mistake. Passing those tests may then conceal a misunderstood requirement. We measure how often code reported as successful fails tests that were not provided to the agent. We call this misma...

EvidenT: An Evidence-Preserving Framework for Iterative System-Level Package Repair

Frequent toolchain updates and the expanding diversity of instruction set architectures (ISAs) have made large-scale system-level software package repair a critical task. Diagnosing and repairing build failures remains challenging due to heterogeneous failure evidence, complex de...

The Python simulations of chemistry framework: 10 years of an open-source quantum chemistry project

Over the past decade, the Python-based Simulations of Chemistry Framework (PySCF) has developed into a widely used open-source platform for electronic-structure theory and quantum chemical method development. This article reviews the major advances since the previous overview in...

The Media Bias Detector: A framework for annotating and analyzing the news

News organizations introduce bias into their coverage via the choices they make about which topics to cover (or ignore) and how to frame the issues they do decide to cover. Here, we introduce the Media Bias Detector, a scalable computational framework that integrates large langua...

Predicting the status of 35 sustainable development goal indicators in Indian villages: a semi-supervised machine learning approach for precision public policy

Background National and district-level monitoring of the Sustainable Development Goals (SDGs) in India obscures substantial inequalities at finer geographic resolutions, such as villages. While villages are central to service delivery and local governance, village-level estimates...

Aquatic predators as complementary tools for mosquito vector control: current evidence, ecological considerations, and future directions

Insecticide-based strategies for mosquito control are increasingly constrained by insecticide resistance, sparking interest in eco-friendly alternatives, one of which is the use of aquatic predators to reduce mosquito densities. Evidence from laboratory, semi-field, and localized...

Seemingly conscious AI risks

AI systems are increasingly designed in ways that lead users to perceive them as conscious. This paper provides a unified framework connecting empirical hallmarks of consciousness attribution to a structured risk taxonomy of Seemingly Conscious AI (SCAI), AI systems that exhibit...